Pedestrian Attribute Analysis Using Agent-Based Modeling

Pedestrian Attribute Detection Using CNN

Learning to determine the attributes of pedestrian using their far-view field images is a challenging problem in visual surveillance. Many previous works have focused on the problem of pedestrian detection. Traditionally SVMs have been a popular choice for pedestrian attribute recognition, however recently there has been interest in using CNNs for this task. In this project we implement traditi...

Using Agent-based Modeling

Agent-Based Modeling Using Erlang

There is a conceptual gap between real world systems and their models created using differential equations. Numerous systems, such as traffic flow, financial markets, neural networks... are all naturally composed of agents interacting with each other and the environment, from which the behavior of such systems emerges. The more complex the interactions and agents, the more difficult, and even i...

Learning to Recognize Pedestrian Attribute

Learning to recognize pedestrian attributes at far distance is a novel research topic in video surveillance scenarios where face and body close-shots are hardly available; instead, only far-view video frames of pedestrian are given. In this study, we present an alternative approach that exploits the context of neighboring pedestrian images for improved attribute inference compared to the conven...

Agent - based simulation of pedestrian behaviour